Computer-aided diagnosis of Parkinson’s disease based on [¹²³I]FP-CIT SPECT binding potential images, using the voxels-as-features approach and support vector machines

Abstract

The achieved classification accuracy was very high and, in fact, higher than accuracies found in previous studies reported in the literature. In addition, results were obtained on a large dataset of early Parkinson's disease subjects. In summation, the information provided by the developed computational solution potentially supports clinical decision-making in nuclear medicine, using important additional information beyond the commonly used uptake ratios and respective statistical comparisons. (ClinicalTrials.gov Identifier: NCT01141023).

Comparison of machine learning and semi-quantification algorithms for (I123)FP-CIT classification: the beginning of the end for semi-quantification?

“…Features are tested for statistical significance (wilcoxon rank) before use in the classifier Linear SVM and SVM with Radial Basis Function (RBF) kernel, Linear Discriminant Analysis (LDA) 350 images from PPMI database (187 healthy controls (HC), 163 PD). 5 fold cross-validation (CV), repeated 100 times Linear SVM: maximum of accuracy = 99.4% RBF kernel: maximum of accuracy = 99.4% LDA: maximum of accuracy = 99.4% Oliveira and Castelo-Branco 2015 [ 32 ] Image voxels within striatal region of interest Linear SVM 654 images from PPMI database (209 HC, 445 PD). Leave-one-out CV Maximum of accuracy = 97.9% Sensitivity = 97.8% Specificity = 98.1% Prashanth et al 2017 [ 33 ] 16 shape and 14 surface fitting features of selected slices, following thresholding.…”

Neuroimaging of Parkinson's disease: Expanding views

“…This finding can help differentiate parkinsonian syndromes (i.e. PD, multiple system atrophy, progressive supranuclear palsy) from essential tremor, or dementia with Lewy bodies (which overlaps diagnosis of PD) from Alzheimer’s disease (Bajaj et al, 2013; Gerasimou et al, 2012; Oliveira et al., 2015; Thiriez et al, 2015). However, it is important to realize that decreased 123 I -FP-CIT identifies the loss of dopaminergic neurons, which is not specific for PD.…”

Extraction, selection and comparison of features for an effective automated computer-aided diagnosis of Parkinson’s disease based on [123I]FP-CIT SPECT images

“…Using cross-validation and SVM based classifiers, Prashanth et al [14] found an accuracy of approximately 96% (96.6% sensitivity and 95.0% specificity) on a PPMI dataset comprising well established pre-computed uptake ratios of 548 subjects. Using SVM and voxel-as-feature (VAF) approach, Illán et al [25] claimed an accuracy of approximately 91% (89% sensitivity and 93% specificity) on a dataset of 208 images, and Oliveira and Castelo-Branco [26] found an accuracy of 98% in a dataset from PPMI very similar to the one used here.…”